Title :
Function optimization using a lattice of neurons
Author_Institution :
Texas Instrum. Inc., Dallas, TX, USA
Abstract :
Summary form only given. A lattice structure of formal neurons is used to search for optimal solutions. A solution vector, encoded by a column of neural units, is associated with each positron in the lattice. A general form of an updating algorithm is presented which modifies solution vectors based on their local comparison with neighborhood solutions. Simulations are performed on four examples.<>
Keywords :
neural nets; optimisation; formal neurons; lattice structure; local comparison; neighborhood solutions; neural nets; neuron lattice; optimal solutions; Neural networks; Optimization methods;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118373
